Видео

Talk given on Sept 16, 2020 for the internal Harvard offering of the Intro to TinyML course. Jane Polak Scowcroft is a New Product Lead at Mozilla. Jane brings international experience in the intersection of deep research, breakthrough technology, policy and new products across all types of organisations - startups, governments and not-for-profits, and industry. With a computer engineering and ...

Talk given on Sept 2, 2020 for the internal Harvard offering of the Intro to TinyML course. Evgeni Gousev is a Senior Director of Qualcomm AI Research. He leads Qualcomm R&D organization in the Silicon Valley Center and is also responsible for developing ultra low power embedded computing and machine learning platform, including always on machine vision. He is a co-founder of tinyML Foundation ...

Talk given on Nov 2, 2020 for the internal Harvard offering of the Intro to TinyML course. Dan leads embedded machine learning engineering at Edge Impulse, a platform that allows developers to train machine learning models that run on tiny, low-power devices. He's co-author of the book TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers, published by O'...

Talk given on Oct 26, 2020 for the internal Harvard offering of the Intro to TinyML course. Danilo Pau, graduated at Politecnico di Milano, on 1992 in Electronic Engineering. He joined SGS-THOMSON (now STMicroelectronics) on 1991 and worked on mpeg2 video memory reduction, then video coding, embedded graphics, computer vision, and currently on deep learning. During his career helped in transfer...

Talk given on Nov 11, 2020 for the internal Harvard offering of the Intro to TinyML course. Erich Plondke has been designing signal processor architectures for almost 20 years. For the last 16 years he has been working at Qualcomm on the Hexagon signal processor architecture. Over 10 billion Hexagon cores have shipped into phones and other devices. For the last several years he has been working...

Talk given on Nov 9, 2020 for the internal Harvard offering of the Intro to TinyML course. Felix Johnny is the maintainer of Arm’s open source CMSIS-NN library that targets optimized Neural Network kernels for Cortex-M CPUs. He has spent most of the last 15 years in the wireless domain working with software design and optimizations in memory and cycle constrained systems. Outside of work, he is...

Talk given on Nov 18, 2020 for the internal Harvard offering of the Intro to TinyML course. Nat is a Software Engineer on the Tensorflow team at Google. He specializes in neural network optimization for embedded devices. Nat represents Google at the TinyMLPerf industry working group, and authored the benchmarking and profiling tools in Tensorflow for Microcontrollers. See more: sites.google.com...

Talk given on Oct 28, 2020 for the internal Harvard offering of the Intro to TinyML course. Pete Warden is the lead of the TensorFlow Mobile/Embedded team, former CTO of Jetpac, acquired by Google in 2014. O'Reilly author, and blogger at petewarden.com. See more: sites.google.com/g.harvard.edu/tinyml/home

Talk given on Oct 5, 2020 for the internal Harvard offering of the Intro to TinyML course. Prateek Jain is a Senior Principal Researcher at Microsoft Research India and an adjunct faculty member at IIT Kanpur. He obtained his PhD degree from the Computer Science department at UT Austin and his BTech degree from IIT Kanpur. He works in the areas of large-scale and non-convex optimization, high-d...

Talk given on Sept 21, 2020 for the internal Harvard offering of the Intro to TinyML course. Dr Sacha Krstulović was a Senior Research Engineer at Nuance’s Advanced Speech Group (Nuance ASG) before joining Audio Analytic. At Nuance, he worked on pushing the limits of large-scale speech recognition services such as Voicemail-to-Text and Voice-Based Mobile Assistants (Apple Siri type services). P...

Talk given on Oct 21, 2020 for the internal Harvard offering of the Intro to TinyML course. Dr. Thierry Moreau is the co-founder of OctoML Inc., a Seattle-based startup that applies state of the art ML-based techniques to make deep learning models faster and easier to put into production. Thierry has been a key contributor to Apache TVM, the open source machine learning compiler that started at...

Talk given on Nov 11, 2020 for the internal Harvard offering of the Intro to TinyML course. Tomas Edsö, Senior Principal Engineer, is currently acting as HW Tech Lead within the Arm machine learning group for the embedded NPU product line. Tomas joined Arm Sweden Lund in 2008 as one of the founding members of the video IP company Logipard, and has a wealth of knowledge within Video standards, d...

Talk given on Dec 2, 2020 for the internal Harvard offering of the Intro to TinyML course. Tulsee Doshi is the product lead for Google’s ML fairness and Responsible AI efforts, where she partners with product teams to drive improvements and develop Google-wide resources and best practices for more inclusive, diverse, and ethical products. Previously, Tulsee worked on the RUclips recommendations...

Talk given on Sept 30, 2020 for the internal Harvard offering of the Intro to TinyML course. Alex is a Principal Software Engineer at Google, where he leads the team of machine learning researchers and engineers who develop the technologies behind hotword detection ("Ok Google"), speaker identification, acoustic echo cancellation, embedded large vocabulary speech recognition, and endpointing an...